Text Pre-process
Description
Section titled “Description”The Text Pre-process step cleans and normalizes a text column. It is the equivalent of the matching Alteryx tool and runs in the workflow engine (the ML / NLP / document libraries run in the executor job).
Source & Options
Section titled “Source & Options”- Source / Output tables — the input data and where the result is written.
- Text column, output column, and toggles (remove digits / punctuation / stopwords, lemmatize).
Columns
Section titled “Columns”The Columns tab maps the input columns passed through to the output.
KNIME Text Processing Nodes
Section titled “KNIME Text Processing Nodes”In the KNIME Text Processing Node group, choose a KNIME Text Node (node) to run one of KNIME’s Text Processing nodes with this step — for example preprocess, tagger, bag_of_words, frequency, document_vector, keywords, topics, language, or the embedding nodes. The node’s own settings, such as Document Column (document_column) and Output Column (output_column), appear beside it in knime_config. Leave the node as (none) to run the step’s own settings. A converted KNIME workflow sets the same keys.
In the KNIME Node Tables group, a node that reads a second table, such as a dictionary, entity list, or vocabulary, reads Second Input Table (source_b) with the columns in Second Table Columns (source_b_columns). A node with further outputs writes them to the tables listed in Further Output Tables (targets), in order.